[1/12] Optimizing prompts for specific tasks has been key to improving LLM performance, but what if we optimize prompts on system level to work well on *all* tasks? Check out 🌱SPRIG, a genetic system prompt optimizer that help unlock LLMs' full potential: arxiv.org/abs/2410.14826

I’m thrilled to be at EMNLP this week presenting our paper, “The Empirical Variability of Narrative Perceptions of Social Media Texts” I’ll be giving an oral presentation during the CSS + Cultural Analytics Session 2 (Nov 14). Paper: aclanthology.org/2024.emnlp-mai… 🧵(1/12)

DO NOT DO THIS. I have previously raised this for Ethics Review when I saw it in a paper. You are not sneaky.

💬 Have you or a loved one compared LM probabilities to human linguistic acceptability judgments? You may be overcompensating for the effect of frequency and length! 🌟 In our new paper, we rethink how we should be controlling for these factors 🧵:

#NLProc Just because GPT-4o is 17 times more expensive than GPT-4o-mini, does that mean it generates synthetic data 17 times better? Introducing the AgoraBench, a benchmark for evaluating data generation capabilities of LMs.

When you interact with ChatGPT, have you wondered if they would ever "lie" to you? We found that in scenarios where truthfulness conflicts with achieving goals, LLMs often choose deception. Our new #NAACL2025 paper, "AI-LIEDAR ," reveals all models tested were truthful less than

I spoke to Forbes about why model "welfare" is a silly framing to an important issue; models don't have feelings, and it's a big distraction from real questions like tensions between safety vs. user utility, which are NLP/HCI/policy questions forbes.com/sites/victorde…

We have been studying these questions of how models should refuse in our recent paper accepted to EMNLP Findings (arxiv.org/abs/2506.00195) led by my wonderful PhD student Mingqian Zheng

Happy to announce that my #EMNLP2025 paper Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design have finally made it to arxiv! This work REDEFINES anthropomorphism in LLM!! arxiv.org/abs/2508.17573…